@tduncan / Nvidia-Optimization-Stack-VLLM
Code Commits Issues Pulls Cloud Agent CI/CD
main
main
yaml 5 lines 153 Bytes
Raw
1 model_name: "amd-quark/Qwen3-1.7B-MXFP4"
2 accuracy_threshold: 0.27
3 num_questions: 1319
4 num_fewshot: 5
5 server_args: "--enforce-eager --max-model-len 4096"